Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5109 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5119. Min Range: -2.5119

Max Act: 2.5119. Min Act: -0.0000

Data Index: 1619397 (Python Code)

Max Activating Token Index: 519

Text #1

Max Range: 2.5119. Min Range: -2.5119

Max Act: 2.4632. Min Act: -0.0000

Data Index: 1406028 (Python Code)

Max Activating Token Index: 576

Text #2

Max Range: 2.5119. Min Range: -2.5119

Max Act: 2.4560. Min Act: -0.0000

Data Index: 1462939 (Python Code)

Max Activating Token Index: 648

Text #3

Max Range: 2.5119. Min Range: -2.5119

Max Act: 2.4645. Min Act: -0.0000

Data Index: 1605821 (Python Code)

Max Activating Token Index: 942

Text #4

Max Range: 2.5119. Min Range: -2.5119

Max Act: 2.2084. Min Act: -0.0000

Data Index: 1047027 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 2.5119. Min Range: -2.5119

Max Act: 2.2601. Min Act: -0.0000

Data Index: 1632554 (Python Code)

Max Activating Token Index: 21

Text #6

Max Range: 2.5119. Min Range: -2.5119

Max Act: 2.3491. Min Act: -0.0000

Data Index: 487936 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 2.5119. Min Range: -2.5119

Max Act: 2.1829. Min Act: -0.0000

Data Index: 1439349 (Python Code)

Max Activating Token Index: 60

Text #8

Max Range: 2.5119. Min Range: -2.5119

Max Act: 2.1945. Min Act: -0.0000

Data Index: 1631242 (Python Code)

Max Activating Token Index: 724

Text #9

Max Range: 2.5119. Min Range: -2.5119

Max Act: 2.0114. Min Act: -0.0000

Data Index: 1572625 (Python Code)

Max Activating Token Index: 205

Text #10

Max Range: 2.5119. Min Range: -2.5119

Max Act: 2.1295. Min Act: -0.0000

Data Index: 1607174 (Python Code)

Max Activating Token Index: 7

Text #11

Max Range: 2.5119. Min Range: -2.5119

Max Act: 2.1378. Min Act: -0.0000

Data Index: 642584 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 2.5119. Min Range: -2.5119

Max Act: 2.1328. Min Act: -0.0000

Data Index: 986792 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 2.5119. Min Range: -2.5119

Max Act: 1.8783. Min Act: -0.0000

Data Index: 1431567 (Python Code)

Max Activating Token Index: 948

Text #14

Max Range: 2.5119. Min Range: -2.5119

Max Act: 2.2036. Min Act: -0.0000

Data Index: 1470462 (Python Code)

Max Activating Token Index: 53

Text #15

Max Range: 2.5119. Min Range: -2.5119

Max Act: 2.0363. Min Act: -0.0000

Data Index: 325867 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 2.5119. Min Range: -2.5119

Max Act: 2.0536. Min Act: -0.0000

Data Index: 264701 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 2.5119. Min Range: -2.5119

Max Act: 2.0502. Min Act: -0.0000

Data Index: 1649506 (Python Code)

Max Activating Token Index: 516

Text #18

Max Range: 2.5119. Min Range: -2.5119

Max Act: 2.1520. Min Act: -0.0000

Data Index: 343026 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 2.5119. Min Range: -2.5119

Max Act: 2.0032. Min Act: -0.0000

Data Index: 1614267 (Python Code)

Max Activating Token Index: 91